bmad-agent-builder

Build, edit, and analyze AI agents through structured conversational discovery and quality validation.

Updated May 5, 2026
One-click install
npx skills add https://github.com/devalexanderdaza/bmad-any --skill bmad-agent-builder-devalexanderdaza
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-agent-builder
Source: https://github.com/devalexanderdaza/bmad-any/tree/main/.agents/skills/bmad-agent-builder
Command: npx skills add https://github.com/devalexanderdaza/bmad-any --skill bmad-agent-builder-devalexanderdaza

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill eliminates the complexity of manually designing AI agent architectures, persona definitions, and capability structures by guiding you through a structured conversational discovery process. Whether you are building a new agent from scratch, analyzing an existing one for quality issues, or refining its behavior, the Skill ensures every agent is outcome-driven, properly scaffolded, and ready for production use.

Core Features & Use Cases

  • Conversational Agent Building: Walk through a six-phase discovery process to design stateless, memory, or autonomous agents with proper personas, capabilities, and sanctum architecture.
  • Quality Analysis: Run comprehensive linting and judgment-based scans to identify structural issues, over-specification, and enhancement opportunities in existing agents.
  • Agent Editing & Rebuilding: Make targeted edits to existing agents or completely rebuild them from core outcomes while preserving what works.
  • Use Case: A developer with a rough idea for a coding coach agent can use this Skill to discover the right agent type, define its mission and personality, generate the complete skill structure with templates, and validate it against quality standards.

Quick Start

Use the bmad-agent-builder skill to create a new memory agent for code review by describing what it should achieve and how it should interact with you.

Frequently Asked Questions about bmad-agent-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design an AI agent architecture through conversational discovery?

You can design an AI agent architecture through conversational discovery by entering a six-phase process that defines personas, capabilities, and sanctum architecture for stateless, memory, or autonomous agents.

Can I analyze existing AI agents for structural issues and over-specification?

Yes, you can analyze existing AI agents by running comprehensive linting and judgment-based scans that identify structural issues, over-specification, and enhancement opportunities across multiple quality dimensions.

What is the best way to scaffold a memory agent for code review?

The best way to scaffold a memory agent is to describe its desired outcomes and interactions, allowing the builder to generate a deterministic skill structure with templates and validate it against quality standards.

Do I need pyyaml installed to build and edit AI agents?

Yes, you need pyyaml installed as a dependency to run the scripts that build, edit, and analyze AI agent skills through the structured conversational discovery and quality validation processes.

How do I rebuild an autonomous agent while preserving its working components?

You can rebuild an autonomous agent from its core outcomes while preserving functioning components by making targeted edits or completely rebuilding the agent structure during the conversational discovery process.

When should I not use automated agent design for skill authoring?

You should avoid automated agent design when your project requires highly customized architectures outside standard stateless, memory, or autonomous patterns, or when deterministic scaffolding cannot accommodate your specific capability routing needs.